Streaming events
Legacy
Realtime Beta
Overview
Sessions
Create a session
Transcription Sessions
Create a transcription session
Completions
Create a completion
API Reference
Copy Markdown
Open in
Claude
Open in
ChatGPT
Open in
Cursor
Copy Markdown
View as Markdown
API Overview
Use this reference to look up OpenAI API endpoints, request and response schemas, streaming events, client library methods, and shared behavior such as authentication, errors, rate limits, and request IDs.
Start here
Section titled “Start here”
Choose the API surface for your application:
Responses
for direct model requests, tool use, audio, image, and text inputs, and stateful interactions.
Realtime API
for low-latency voice or audio sessions over WebRTC, WebSocket, or SIP.

Use the
client events
and
server events
references while building sessions.
Administration
for organization workflows such as users, invites, projects, API keys, and audit logs.
Create credentials. Use a standard
API key
for application requests, an
Admin API key
for Administration endpoints, or
workload identity federation
for short-lived access tokens.
Install an official client library from the
libraries page
, or call the HTTP API directly from any environment that supports HTTP requests.
Make a first request with the
developer quickstart
or go straight to the
Responses create reference
.
Before production, review
error codes
,
rate limits
, and request ID logging below.
